Plan guide

How much coding do you get from OpenCode Go?

Available models: Haiku 5.5 / GPT-6 Luna / GLM-5.3-Flash / GLM-5.3 / MiniMax M3.1 / LongCat 2.0 / Muse Spark 1.3 Contributor / Grok 4.7 / Gemini 4 Argon / Qwen 3.8 Max / Qwen 3.8 Flash / Qwen 3.7 Plus / Kimi K3.1 / Kimi K2.7 Code / DeepSeek V4.1 Flash / DeepSeek V4 Pro / MiMo V2.6 Flash / MiMo V2.6 Pro / Hy4 / Hy4 preview — Latest model in each supported family shown. Allowances differ by model; available models do not imply interchangeable usage quotas.. $10/mo buys about 20 h/week of building at p50 peak (p10–p90 10–40) (source: official-dollar). Not measured: this plan has no verified agent/model evaluation in the current suite, so it is excluded from the stack builder's ranking. Catalog note: Windows $12/5h, $30/week, $60/month. DeepSeek Flash on Go is 2× dearer in the Asian peak (your morning).

Hours by role

p10 / p50 / p90, h/week, at the plan's own clock. Peak and off-peak differ only where the vendor publishes a night rate.

RoleBenchmark quality /100Peak p10 / p50 / p90 (h/week)Off-peak p10 / p50 / p90 (h/week)
Planningnot measured4 / 8 / 16—
Buildingnot measured10 / 20 / 40—
Adminnot measured20 / 40 / 80—

Clock: no published off-peak discount. Runs as a CLI agent. Source: official-dollar.